Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 230 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9166. Min Range: -0.9166

Max Act: 0.9166. Min Act: -0.0001

Data Index: 1002200 (C4 (Web Text))

Max Activating Token Index: 157

Text #1

Max Range: 0.9166. Min Range: -0.9166

Max Act: 0.8629. Min Act: -0.0000

Data Index: 288085 (C4 (Web Text))

Max Activating Token Index: 559

Text #2

Max Range: 0.9166. Min Range: -0.9166

Max Act: 0.8769. Min Act: -0.0000

Data Index: 482272 (C4 (Web Text))

Max Activating Token Index: 934

Text #3

Max Range: 0.9166. Min Range: -0.9166

Max Act: 0.6250. Min Act: -0.0000

Data Index: 779902 (C4 (Web Text))

Max Activating Token Index: 579

Text #4

Max Range: 0.9166. Min Range: -0.9166

Max Act: 0.7450. Min Act: -0.0000

Data Index: 584106 (C4 (Web Text))

Max Activating Token Index: 668

Text #5

Max Range: 0.9166. Min Range: -0.9166

Max Act: 0.7922. Min Act: -0.0000

Data Index: 271756 (C4 (Web Text))

Max Activating Token Index: 772

Text #6

Max Range: 0.9166. Min Range: -0.9166

Max Act: 0.7673. Min Act: -0.0001

Data Index: 447156 (C4 (Web Text))

Max Activating Token Index: 912

Text #7

Max Range: 0.9166. Min Range: -0.9166

Max Act: 0.6968. Min Act: -0.0000

Data Index: 984966 (C4 (Web Text))

Max Activating Token Index: 663

Text #8

Max Range: 0.9166. Min Range: -0.9166

Max Act: 0.7845. Min Act: -0.0000

Data Index: 571039 (C4 (Web Text))

Max Activating Token Index: 322

Text #9

Max Range: 0.9166. Min Range: -0.9166

Max Act: 0.7271. Min Act: -0.0001

Data Index: 1046939 (C4 (Web Text))

Max Activating Token Index: 826

Text #10

Max Range: 0.9166. Min Range: -0.9166

Max Act: 0.7085. Min Act: -0.0000

Data Index: 1301764 (C4 (Web Text))

Max Activating Token Index: 241

Text #11

Max Range: 0.9166. Min Range: -0.9166

Max Act: 0.7124. Min Act: -0.0001

Data Index: 1297837 (C4 (Web Text))

Max Activating Token Index: 866

Text #12

Max Range: 0.9166. Min Range: -0.9166

Max Act: 0.7129. Min Act: -0.0001

Data Index: 620132 (C4 (Web Text))

Max Activating Token Index: 194

Text #13

Max Range: 0.9166. Min Range: -0.9166

Max Act: 0.7337. Min Act: -0.0000

Data Index: 234385 (C4 (Web Text))

Max Activating Token Index: 707

Text #14

Max Range: 0.9166. Min Range: -0.9166

Max Act: 0.7720. Min Act: -0.0000

Data Index: 432688 (C4 (Web Text))

Max Activating Token Index: 414

Text #15

Max Range: 0.9166. Min Range: -0.9166

Max Act: 0.7569. Min Act: -0.0000

Data Index: 137996 (C4 (Web Text))

Max Activating Token Index: 134

Text #16

Max Range: 0.9166. Min Range: -0.9166

Max Act: 0.7156. Min Act: -0.0001

Data Index: 722525 (C4 (Web Text))

Max Activating Token Index: 162

Text #17

Max Range: 0.9166. Min Range: -0.9166

Max Act: 0.7193. Min Act: -0.0000

Data Index: 776073 (C4 (Web Text))

Max Activating Token Index: 393

Text #18

Max Range: 0.9166. Min Range: -0.9166

Max Act: 0.7356. Min Act: -0.0000

Data Index: 108301 (C4 (Web Text))

Max Activating Token Index: 415

Text #19

Max Range: 0.9166. Min Range: -0.9166

Max Act: 0.6931. Min Act: -0.0000

Data Index: 173568 (C4 (Web Text))

Max Activating Token Index: 1002